%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
MN 2407 DSK QwQify V0.1 12B
This is a test model fine-tuned based on PocketDoc/Dans-SakuraKaze-V1.0.0-12b, designed to imbue existing models with a QwQ mindset, suitable for role-playing/adventure/collaborative writing scenarios.
Downloads 734
Release Time : 3/15/2025
Model Overview
This model is fine-tuned from PocketDoc/Dans-SakuraKaze-V1.0.0-12b (a role-playing/adventure/collaborative writing model) using LoRA technology to give it a QwQ mindset. Primarily used for dialogue generation and collaborative writing tasks.
Model Features
QwQ mindset
Through fine-tuning, the model is given the unique QwQ way of thinking and expression, enabling it to exhibit a specific style in dialogues and writing.
Role-playing optimization
Specially optimized for role-playing scenarios, capable of generating dialogue content that fits character settings.
Collaborative writing support
Suitable for collaborative writing tasks, able to generate coherent text content based on context.
ChatML format support
Uses the ChatML prompt format for easier dialogue management and context control.
Model Capabilities
Text generation
Role-playing dialogue
Collaborative writing
Stylized text generation
Use Cases
Entertainment
Role-playing games
Engage in dialogue interactions as an NPC in games
Generate natural dialogues that fit character settings
Interactive story creation
Co-create interactive stories with users
Generate coherent storylines that fit the context
Creative writing
Collaborative writing assistant
Assist writers in creative writing
Provide creative suggestions and text continuations
đ BeaverAI/MN-2407-DSK-QwQify-v0.1-12B
A test model aiming to endow an existing model with QwQ's thoughts.
đ Quick Start
This model, BeaverAI/MN-2407-DSK-QwQify-v0.1-12B, is a test model designed to infuse an existing model with QwQ's thoughts. It is built upon the foundation of the PocketDoc/Dans-SakuraKaze-V1.0.0-12b model, which is an rp/adventure/co - writing model. This base model was in turn trained on the PocketDoc/Dans-PersonalityEngine-V1.1.0-12b model, a versatile instruct model, which itself was trained on the mistralai/Mistral-Nemo-Base-2407 model.
Usage Instructions
- Prompt Formatting: The prompt formatting and usage should be consistent with that of QwQ. Use ChatML and remove the thinking from previous turns. If thoughts aren't being generated automatically, add
<think>\nat the start of the assistant turn. - Formatting Follow - up: The model should follow the formatting of previous model turns. In the first few turns of the conversation, you may need to regenerate responses several times and might want to edit the model's responses to suit your preferences.
- Prefix Settings: You may want to disable inserting the
{{char}}:prefix for the character. Instead, add something likeOnly speak as "{{char}}" in conversation with "{{user}}". Output your final response with a "{{char}}:" prefix.to the end of your system prompt.
⨠Features
This model is a fine - tuned version of PocketDoc/Dans-SakuraKaze-V1.0.0-12b on multiple datasets, including:
- PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
- PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
- ... (a total of 10 datasets)
It achieves a loss of 1.2770 on the evaluation set.
đ Documentation
Axolotl Config
See axolotl config
axolotl version: 0.8.0.dev0
mlflow_tracking_uri: http://127.0.0.1:7860
mlflow_experiment_name: MN-2407-DSK-QwQify-v0.1-12B-LoRA
# Hugging Face saving config
hub_model_id: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS
hub_strategy: every_save
# Model checkpointing config
output_dir: ./Outputs/MN-2407-DSK-QwQify-v0.1-12B-LoRA
resume_from_checkpoint:
save_steps: 25
save_safetensors: true
save_total_limit: 3
save_only_model: false
# Model architecture config
base_model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
model_type: MistralForCausalLM
tokenizer_type: PreTrainedTokenizerFast
# Mixed precision training config
bf16: true
fp16: false
tf32: false
# Model loading config
load_in_8bit: false
load_in_4bit: false
strict: false
# Sequence config
sequence_len: 8192
min_sample_len: 256
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false
# LoRA adapter config
adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.125
peft_layers_to_transform:
peft_use_dora:
peft_use_rslora:
peft_layer_replication:
lora_target_modules:
- gate_proj
- down_proj
- up_proj
- q_proj
- v_proj
- k_proj
- o_proj
lora_modules_to_save:
# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
fix_untrained_tokens:
# Dataset config
# https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
datasets:
- path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
split: train
type: customchatml-regex-last-only
- path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
split: train
type: customchatml-regex-last-only
- path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
split: train
type: customchatml-regex-last-only
- path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
split: train
type: customchatml-regex-last-only
- path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
split: train
type: customchatml-regex-last-only
- path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
split: train
type: customchatml-regex-last-only
- path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
split: train
type: customchatml-regex-last-only
- path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
split: train
type: customchatml-regex-last-only
- path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
split: train
type: customchatml-regex-last-only
- path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
split: train
type: customchatml-regex-last-only
test_datasets:
- path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
split: test
type: customchatml-regex-last-only
- path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
split: test
type: customchatml-regex-last-only
- path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
split: test
type: customchatml-regex-last-only
- path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
split: test
type: customchatml-regex-last-only
- path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
split: test
type: customchatml-regex-last-only
- path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
split: test
type: customchatml-regex-last-only
- path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
split: test
type: customchatml-regex-last-only
- path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
split: test
type: customchatml-regex-last-only
- path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
split: test
type: customchatml-regex-last-only
- path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
split: test
type: customchatml-regex-last-only
val_set_size: 0
eval_strategy: steps
eval_steps: 25
dataset_prepared_path: ./00-Tokenized-Datasets/MN-2407-DSK-QwQify-v0.1-12B-customchatml-regex-last-only
shuffle_merged_datasets: true
dataset_processes:
# Training hyperparameters
num_epochs: 2
gradient_accumulation_steps: 1
micro_batch_size: 16 # x4 GPUs = 64
eval_batch_size: 16 # x4 GPUs = 64
warmup_steps: 0
optimizer: came_pytorch
optim_args:
optim_target_modules:
lr_scheduler: rex
learning_rate: 2e-5
cosine_min_lr_ratio:
loraplus_lr_ratio:
loraplus_lr_embedding:
weight_decay: 0.1
max_grad_norm: 1
logging_steps: 1
# Model optimization
gradient_checkpointing: unsloth
flash_attention: true
plugins:
- axolotl.integrations.liger.LigerPlugin
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_cross_entropy: false
liger_fused_linear_cross_entropy: false
lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false
# DeepSpeed
deepspeed: deepspeed_configs/zero3_bf16.json
# Garbage Collection
gc_steps: 1
# Debug config
debug: true
seed: 42
# Token config
special_tokens:
bos_token: "<s>"
eos_token: "<|im_end|>"
pad_token: "<pad>"
tokens:
Model Details
This model, MN-2407-DSK-QwQify-v0.1-12B-LoRA-WS, is a fine - tuned version of PocketDoc/Dans-SakuraKaze-V1.0.0-12b on multiple datasets.
Training and Evaluation
Training Hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi - GPU
- num_devices: 4
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 2.0
Training Results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.134 | 0.0038 | 1 | 2.0025 |
| 1.6185 | 0.0951 | 25 | 1.5748 |
| 1.5187 | 0.1901 | 50 | 1.4871 |
| 1.4757 | 0.2852 | 75 | 1.4410 |
| 1.4008 | 0.3802 | 100 | 1.4100 |
| 1.4116 | 0.4753 | 125 | 1.3857 |
| 1.357 | 0.5703 | 150 | 1.3630 |
| 1.3435 | 0.6654 | 175 | 1.3478 |
| 1.3332 | 0.7605 | 200 | 1.3353 |
| 1.3042 | 0.8555 | 225 | 1.3308 |
| 1.2993 | 0.9506 | 250 | 1.3228 |
| 1.3105 | 1.0456 | 275 | 1.3154 |
| 1.2782 | 1.1407 | 300 | 1.3094 |
| 1.3063 | 1.2357 | 325 | 1.3070 |
| 1.3003 | 1.3308 | 350 | 1.3005 |
| 1.2937 | 1.4259 | 375 | 1.2952 |
| 1.283 | 1.5209 | 400 | 1.2922 |
| 1.2692 | 1.6160 | 425 | 1.2887 |
| 1.2639 | 1.7110 | 450 | 1.2855 |
| 1.2546 | 1.8061 | 475 | 1.2822 |
| 1.2711 | 1.9011 | 500 | 1.2787 |
| 1.2492 | 1.9962 | 525 | 1.2770 |
Framework Versions
- PEFT 0.14.0
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.1
đ License
This project is licensed under the Apache-2.0 license.
Phi 2 GGUF
Other
Phi-2 is a small yet powerful language model developed by Microsoft, featuring 2.7 billion parameters, focusing on efficient inference and high-quality text generation.
Large Language Model Supports Multiple Languages
P
TheBloke
41.5M
205
Roberta Large
MIT
A large English language model pre-trained with masked language modeling objectives, using improved BERT training methods
Large Language Model English
R
FacebookAI
19.4M
212
Distilbert Base Uncased
Apache-2.0
DistilBERT is a distilled version of the BERT base model, maintaining similar performance while being more lightweight and efficient, suitable for natural language processing tasks such as sequence classification and token classification.
Large Language Model English
D
distilbert
11.1M
669
Llama 3.1 8B Instruct GGUF
Meta Llama 3.1 8B Instruct is a multilingual large language model optimized for multilingual dialogue use cases, excelling in common industry benchmarks.
Large Language Model English
L
modularai
9.7M
4
Xlm Roberta Base
MIT
XLM-RoBERTa is a multilingual model pretrained on 2.5TB of filtered CommonCrawl data across 100 languages, using masked language modeling as the training objective.
Large Language Model Supports Multiple Languages
X
FacebookAI
9.6M
664
Roberta Base
MIT
An English pre-trained model based on Transformer architecture, trained on massive text through masked language modeling objectives, supporting text feature extraction and downstream task fine-tuning
Large Language Model English
R
FacebookAI
9.3M
488
Opt 125m
Other
OPT is an open pre-trained Transformer language model suite released by Meta AI, with parameter sizes ranging from 125 million to 175 billion, designed to match the performance of the GPT-3 series while promoting open research in large-scale language models.
Large Language Model English
O
facebook
6.3M
198
1
A pretrained model based on the transformers library, suitable for various NLP tasks
Large Language Model
Transformers
Transformers1
unslothai
6.2M
1
Llama 3.1 8B Instruct
Llama 3.1 is Meta's multilingual large language model series, featuring 8B, 70B, and 405B parameter scales, supporting 8 languages and code generation, with optimized multilingual dialogue scenarios.
Large Language Model Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesL
meta-llama
5.7M
3,898
T5 Base
Apache-2.0
The T5 Base Version is a text-to-text Transformer model developed by Google with 220 million parameters, supporting multilingual NLP tasks.
Large Language Model Supports Multiple Languages
T
google-t5
5.4M
702
Featured Recommended AI Models
Š 2025AIbase